CN115862793A - Apparatus and method for cardiovascular medical data analysis, computer storage medium - Google Patents
Apparatus and method for cardiovascular medical data analysis, computer storage medium Download PDFInfo
- Publication number
- CN115862793A CN115862793A CN202310166383.9A CN202310166383A CN115862793A CN 115862793 A CN115862793 A CN 115862793A CN 202310166383 A CN202310166383 A CN 202310166383A CN 115862793 A CN115862793 A CN 115862793A
- Authority
- CN
- China
- Prior art keywords
- thrombus
- timi
- data analysis
- index
- onset
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The present application relates to an apparatus and method, computer storage medium, for cardiovascular medical data analysis. The device for cardiovascular medical data analysis comprises: the system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring statistical data and clinical data of a myocardial infarction patient, the statistical data at least comprises age, gender, BMI and concurrent diseases, and the clinical data at least comprises: diagnostic results, laboratory test results; the calculation module is used for calculating the high thrombus load state of the patient through a pre-trained model based on statistical data and clinical data; the first confirming module is used for confirming the TIMI thrombus grade corresponding to the high thrombus load state according to the TIMI thrombus grading data; and a determination module for determining a manner of applying the anti-thrombotic therapy based on the TIMI thrombus level. The technical scheme of the application can judge the treatment mode according to the state of illness of the cardiovascular disease patient, effectively reduce surgical complications, improve the prognosis of the patient and improve the treatment effect.
Description
Technical Field
The present application relates to the field of medical data analysis. In particular, the present application relates to an apparatus and method, computer storage medium, for cardiovascular medical data analysis.
Background
The burden of cardiovascular disease in the elderly continues to increase and patients with cardiovascular disease need to receive treatment after the onset of the disease. Surgery directly after the patient's invention may be associated with surgical complications and an unsatisfactory clinical outcome, even with the risk of patient death. However, there is no effective solution for reducing the risk of surgical complications and it is difficult to determine factors that affect clinical outcome.
CN107301326A discloses a personalized disease risk grade analysis method based on conventional factors, comprising: establishing a conventional factor logic table according to the medical information and the big data information, and adjusting in real time according to the updating of the medical information and/or the big data information; acquiring personal information; screening out the personalized factors, setting weights of the personalized factors, and sequencing the personalized factors according to the weights to obtain personal labels, wherein the personal labels comprise an initial disease group, and the initial disease group comprises at least one disease name and a risk level corresponding to the disease name; acquiring personal updating information, and acquiring a personal updating label according to the personal updating information, wherein the personal updating label comprises an updated disease group, and the updated disease group comprises at least one disease name and a risk level corresponding to the disease name; when the updated disease group includes the same disease name as the initial disease group, the updated disease group includes a trend of change of the same disease name.
CN107491651B discloses a self-health management method based on personalized factors, comprising: the method comprises the steps of establishing a pathogenic factor database according to medical information and big data information, establishing a guidance suggestion database according to the medical information, establishing a user information database according to personal information of a user, establishing a primary logic table to obtain a reference guidance suggestion of the user, establishing a secondary logic table to obtain a staged guidance suggestion of the user, establishing a tertiary logic table and performing daily monitoring on the user to obtain a daily guidance suggestion of the user, and adjusting the daily guidance suggestion of the user according to the updating of the medical information, the big data information and the personal information of the user, so that the user can perform self management on diet, movement, emotion and the like according to the staged guidance suggestion and the daily guidance suggestion provided by the method, and the individuation degree and the real-time of self health management are improved.
CN107526931A discloses a health assessment method based on personalized factors, which establishes a conventional factor library according to authoritative literature guide information; the personal information of the user is brought into a conventional factor library to obtain an A-type evaluation result of the user, and the user is dynamically monitored according to variable information in the A-type evaluation result of the user to obtain a B-type evaluation result of the user; establishing a primary logic table according to personal information and medical guidance information of the user, and bringing the A-type evaluation result and the B-type evaluation result into the primary logic table to obtain a C-type guidance result of the user; establishing a secondary logic table according to the medical guidance information, and bringing the C-type guidance result into the secondary logic table to obtain a comprehensive guidance system of the user; and acquiring a health guidance report of the user according to the comprehensive guidance system of the user and the dynamic feedback information of the user. The technical scheme solves the problems of low individuation and poor real-time performance of the existing health assessment.
The above prior art provides a data integration approach for health assessment, but does not provide a direct health assessment output method, and patients and physicians cannot obtain a direct diagnostic and therapeutic reference "list" and data, particularly for TIMI assessment and prediction.
Disclosure of Invention
The embodiment of the application provides a device and a method for cardiovascular medical data analysis and a computer storage medium, which at least solve the problem that the effect of treating patients with cardiovascular diseases is not ideal in the prior art.
According to an aspect of an embodiment of the present application, there is provided an apparatus for cardiovascular medical data analysis, including: a first obtaining module, configured to obtain statistical data and/or clinical data of a myocardial infarction patient, where the statistical data at least includes age, gender, BMI, and complications, and the clinical data at least includes: diagnostic results, laboratory test results; the calculation module is used for calculating the high thrombus load state of the patient through a pre-trained model based on statistical data and clinical data; the first confirming module is used for confirming the TIMI thrombus grade corresponding to the high thrombus load state according to the TIMI thrombus grading data; and a determination module for determining whether to apply or how to apply an anti-thrombotic therapy based on the TIMI thrombus level.
In such a way, the cardiovascular medical data analysis realized by machine learning is introduced, and whether antithrombotic therapy is applied to the myocardial infarction patient is judged according to the detailed illness state of the myocardial infarction patient, so that the burden of determining a therapy mode is reduced, the risk of cardiovascular disease complications is reduced, and the therapy effect is improved. Machine learning approaches that analyze large data make it easy to determine high thrombus loading conditions.
According to an exemplary embodiment of the application, the concurrent disease is selected from one or more of hypertension, cardiogenic shock, atrial fibrillation and periodontal disease.
In this way, several known complications associated with myocardial infarction are set for cardiovascular medical data analysis, whereby more accurate data analysis results can be obtained through machine learning.
According to an exemplary embodiment of the present application, the TIMI thrombus level is calculated using the following formula: TIMI =5 t/(1 + t), t = e ^ (0.0605 + age index +0.1048 + sex index +1.2045 + hypertension index-0.0578 + bmi index-0.3305 + cardiogenic shock onset index-0.5592 + atrial fibrillation onset index-0.7823 + periodontal disease onset index), and t represents a high thrombotic load state.
In this way, the TIMI thrombus level can be calculated by means of data analysis, resulting in a result similar to the TIMI thrombus level experimentally measured, and obtaining a TIMI thrombus level is more efficient.
According to an exemplary embodiment of the application, the determining module comprises: a first judgment unit for determining to apply an intensive antithrombotic therapy if the TIMI thrombus level is greater than or equal to level 3; and a second determination unit for determining to apply a conventional anti-thrombotic therapy if the TIMI thrombus level is less than grade 3.
In this way, by determining whether or not to apply the antithrombotic treatment by judging the thrombus state, the execution standard is effective and accurate, and the data is easily obtained.
According to an exemplary embodiment of the application, the apparatus for cardiovascular medical data analysis further comprises: the second acquisition module is used for acquiring the attack time and the attack time reference value of the myocardial infarction patient; the comparison module is used for comparing the attack time with the attack time reference value to obtain an attack time comparison result; and a second confirmation module for determining whether to apply percutaneous coronary intervention based on the morbidity time comparison result.
In this way, whether to apply percutaneous coronary intervention treatment is determined based on the attack time of the myocardial infarction patient, the risk of complications brought to the treatment of the myocardial infarction patient is reduced, and the treatment effect is improved.
According to an exemplary embodiment of the application, the second confirmation module comprises: a first confirming unit for determining to apply percutaneous coronary intervention if the onset time comparison result indicates that the onset time is greater than the onset time reference value; and a second confirming unit for determining that the percutaneous coronary intervention is not applied if the onset time comparison result indicates that the onset time is less than or equal to the onset time reference value.
In this way, the comparison of the attack time with the attack time reference value is performed, enabling an automatic determination of whether or not to apply a percutaneous coronary intervention, thereby increasing the ease of use of the data analysis device.
According to another aspect of the embodiments of the present application, there is also provided a method for cardiovascular medical data analysis, which is applied to any one of the above apparatuses for cardiovascular medical data analysis, the method for cardiovascular medical data analysis includes: step S10, obtaining statistical data and clinical data of the myocardial infarction patient, wherein the statistical data at least comprises age, gender, BMI and concurrent diseases, and the clinical data at least comprises: diagnostic results, laboratory test results; step S20, calculating the high thrombus load state of the patient through a pre-trained model based on statistical data and clinical data; step S30, confirming a TIMI thrombus grade corresponding to a high thrombus load state according to the TIMI thrombus grading data; and a step S40 of determining a mode of applying an antithrombotic therapy based on the TIMI thrombus level calculated by using the following formula: TIMI =5 t/(1 + t), t = e ^ (0.0605 + age index +0.1048 + sex index +1.2045 + hypertension index-0.0578 + bmi index-0.3305 + cardiogenic shock onset index-0.5592 + atrial fibrillation onset index-0.7823 + periodontal disease onset index), and t represents a high thrombotic load state.
In such a way, the cardiovascular medical data analysis realized by machine learning is introduced, and whether antithrombotic therapy is applied to the myocardial infarction patient is judged according to the detailed illness state of the myocardial infarction patient, so that the burden of determining a therapy mode is reduced, the risk of cardiovascular disease complications is reduced, and the therapy effect is improved. Machine learning approaches that analyze large data make it easy to determine high thrombus burden status and TIMI thrombus levels.
According to an exemplary embodiment of the present application, the step S40 of determining the manner of applying the anti-thrombotic therapy based on the TIMI thrombus level comprises: step S41, if the TIMI thrombus level is more than or equal to 3, determining to apply the intensified antithrombotic therapy; and step S42, determining to apply a conventional antithrombotic therapy if the TIMI thrombus level is less than grade 3.
In this way, whether or not the antithrombotic treatment is applied is determined by judging the thrombus state, the execution standard is effective and accurate, and the data is easy to acquire.
According to an exemplary embodiment of the application, the method of cardiovascular medical data analysis further comprises: acquiring the attack time and an attack time reference value of a myocardial infarction patient; comparing the attack time with an attack time reference value to obtain an attack time comparison result; and determining whether to apply percutaneous coronary intervention based on the time of onset comparison.
In this way, whether to apply percutaneous coronary intervention treatment is determined based on the attack time of the myocardial infarction patient, the risk of complications brought to the treatment of the myocardial infarction patient is reduced, and the treatment effect is improved.
According to an exemplary embodiment of the present application, determining whether to apply percutaneous coronary intervention treatment based on the morbidity time comparison result includes: if the disease onset time comparison result indicates that the disease onset time is greater than the disease onset time reference value, determining to apply percutaneous coronary intervention treatment; and determining that the percutaneous coronary intervention is not applied if the onset time comparison result indicates that the onset time is less than or equal to the onset time reference value.
In this way, the comparison of the attack time with the attack time reference value is performed, enabling an automatic determination of whether or not to apply a percutaneous coronary intervention, thereby increasing the ease of use of the data analysis device.
According to an exemplary embodiment of the application, an apparatus for cardiovascular medical data analysis comprises a computer storage medium comprising computer readable instructions which, when executed by one or more processors, perform the method of any of the above.
According to an example embodiment of the present application, a computer storage medium includes computer readable instructions that, when executed by one or more processors, perform the method of any one of the above.
In the embodiment of the application, a technical scheme of cardiovascular medical data analysis realized by machine learning for analyzing big data is provided, so that the technical problem that the treatment effect on patients with cardiovascular diseases is not ideal is at least solved, and the technical effects of reducing the burden of determining a treatment mode for patients with cardiovascular diseases, reducing the risk of complications of cardiovascular diseases and easily determining a high thrombus load state are realized.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a block diagram of an apparatus for cardiovascular medical data analysis according to an embodiment of the present application;
FIG. 2 is a block diagram of an apparatus for cardiovascular medical data analysis according to an exemplary embodiment of the present application;
fig. 3 is a block diagram of an apparatus for cardiovascular medical data analysis according to another exemplary embodiment of the present application;
fig. 4 is a block diagram of an apparatus for cardiovascular medical data analysis according to yet another exemplary embodiment of the present application;
FIG. 5 is a flow chart of a method of cardiovascular medical data analysis according to an embodiment of the present application;
fig. 6 is a flow chart of a method of cardiovascular medical data analysis according to an exemplary embodiment of the present application.
Description of reference numerals:
1: a cardiovascular medical data analysis device;
11: a first acquisition module;
12: a second acquisition module;
13: a calculation module;
14: a comparison module;
15: a first confirmation module;
16: a second confirmation module;
161: a first confirmation unit;
163: a second confirmation unit;
17: a judgment module;
171: a first judgment unit;
173: a second judgment unit;
s10, S20, S30, S40, S41, S42: step (ii) of
Detailed Description
In order to make the technical solutions better understood by those skilled in the art, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only partial embodiments of the present application, but not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
It should be noted that the terms "first," "second," and the like in the description and claims of this application and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are capable of operation in sequences other than those illustrated or described herein. Moreover, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules or elements is not necessarily limited to those steps or modules or elements expressly listed, but may include other steps or modules or elements not expressly listed or inherent to such process, method, article, or apparatus.
The technical scheme of the application has the following related terms:
RTB: normal thrombus loading;
HTB: high thrombus burden;
PCI: percutaneous coronary intervention;
STEMI: ST-segment elevation myocardial infarction;
ACS: acute coronary syndrome;
AMI: acute myocardial infarction;
MACE: major adverse cardiovascular events.
Prognosis: in medicine, "prognosis" refers to empirically predicted disease progression.
According to an embodiment of the present application, there is provided an apparatus for cardiovascular medical data analysis. Fig. 1 is a block diagram of an apparatus for cardiovascular medical data analysis according to an embodiment of the present application. As shown in fig. 1, an apparatus 1 for cardiovascular medical data analysis according to an exemplary embodiment of the present application includes: the device comprises a first acquisition module 11, a calculation module 13, a first confirmation module 15 and a judgment module 17. The apparatus for cardiovascular medical data analysis may include a processor and a memory, the memory storing computer readable instructions, the processor executing the computer readable instructions to implement the functions of the various modules included in the apparatus. The apparatus is, for example, various smart devices, such as a computer, a tablet, a smart phone, an industrial personal computer, etc., as long as the functions of the respective modules can be executed, and a specific implementation manner thereof is not limited thereto.
In the embodiments of the present application, an example of cardiovascular disease is myocardial infarction. More specifically, an example of cardiovascular disease is STEMI (ST-elevation myocardial infarction). It is understood that myocardial infarction, or further STEMI, is only an example of a cardiovascular disease in the present application. After reading the application, it should be understood that the technical scheme of the application adopts machine learning and big data to analyze patient data, so as to obtain a trained machine model, obtain a data analysis result obtained through the machine learning, and give a judgment result whether to apply antithrombotic therapy and other therapies to cardiovascular diseases, so that the technical scheme of the application can be used for data analysis related to STEMI and can be applied to various cardiovascular diseases. For example, in an exemplary embodiment, the cardiovascular disease is ACS (acute coronary syndrome).
The first obtaining module 11 is configured to obtain statistical data and clinical data of a myocardial infarction patient, where the statistical data at least includes age, gender, BMI (body mass index), and concurrent diseases, and the clinical data at least includes: diagnostic results, laboratory test results. The difference in gender and age of the users will affect that different users will have different resistance to the same disease, which is the fundamental data for medical data analysis. In addition, the name of the user can be obtained to further obtain detailed identity information, or other relevant personal identity data can be obtained from other platforms registered by the user by using the personal identity data. For example, BMI, complications, etc. may be obtained from a patient's medically-related APP, or may be obtained from a patient's medical record. The concurrent disease is a disease which is further suffered by a patient on the basis of suffering from cardiovascular diseases because the patient already suffers from the cardiovascular diseases or a disease with a possibly increased prevalence rate due to suffering from the cardiovascular diseases. The relevant data may also be obtained from the patient's social network, for example, from the patient's attention list, historical access data, query history, posted posts, and the like. The clinical data may be obtained from a hospital system where the patient is hospitalized, or may be provided directly by the physician. The diagnosis result is, for example, disease data obtained by diagnosing a patient, such as the type of disease, the time of infection, and symptoms. The laboratory test result is a result of performing laboratory analysis on a sample collected from a patient, for example, a result of performing a test on a blood sample of the patient, performing dialysis on the patient, and the like, and performing diagnosis using medical equipment. In an exemplary embodiment, the statistical data may also include lifestyle data, such as whether the patient smokes, fitness, and dietary structure, etc., which are considered in the present solution to affect the patient's high thrombotic load.
Table 1 is an example of statistical and clinical data for a myocardial infarction patient, and it should be understood that the technical solution is not limited thereto.
Table 1:
BP = blood pressure.
The calculation module 13 is used to calculate the high thrombus burden state of the patient based on statistical data and clinical data through a pre-trained model. Statistical data and clinical data of over three thousand patients and the corresponding high thrombus load state of the patient are used as input for training a machine model, and the patient suffers from AMI (acute myocardial infarction). The high thrombus loading state is a numerical reading in an application of the embodiment wherein a higher reading is representative of a higher high thrombus loading state. For example, the reading of the high thrombus burden state is set to 0-5 in the training data set according to the actual thrombus burden state of each case, 0 representing no thrombus and 5 representing total occlusion. In practical cases of the technical solution of the present application, a higher high thrombus load state brings a greater treatment risk than a lower high thrombus load state. The trained model, when applied, can output a corresponding high thrombus burden state based on newly entered patient statistical and clinical data. In an exemplary embodiment, in particular, a reading is output that is indicative of a high thrombus loading condition. In another exemplary embodiment, in particular, a graded data representing a high thrombus loading state is output, e.g., high, medium, low, etc.
The first confirming module 15 is configured to confirm a TIMI thrombus level corresponding to a high thrombus load state according to the TIMI thrombus classification data.
In an exemplary embodiment, the high thrombotic loading state further comprises data for confirming a TIMI thrombus grade corresponding to the high thrombotic loading state (TIMI thrombus staging data). The TIMI thrombus grading data, or TIMI blood flow grading, refers to the condition displayed by a contrast medium at the far end of a coronary artery blood vessel in the coronary angiography process to judge the pathological state of the blood vessel. In the present application, in TIMI thrombus grade 0, there is no angiographic characterization of the thrombus. In a TIMI grade 1 thrombus, a thrombus may be present and angiographic features such as reduced contrast density, blurring, irregular lesion contours, or the appearance of a smooth, bulging "meniscus" at the site of total occlusion suggest but fail to diagnose a thrombus. In TIMI grade 2 thrombi, there is a well-defined thrombus with a maximum linear diameter less than or equal to 1/2 of the vessel diameter. There is a definite thrombus in TIMI grade 3 thrombi, but the maximum linear diameter is greater than 1/2 vessel diameter, but less than 2 vessel inner diameters. In the TIMI grade 4 thrombus, the thrombus was clearly observed, and the maximum linear diameter was 2 or more vessel inner diameters. In TIMI 5 grade thrombi, there are totally occluded thrombi.
In another exemplary embodiment, a TIMI blood flow grade of 4 is used. Level 0: it means that the distal end of the vessel is not filled with contrast agent, indicating that there is no perfusion of blood flow at the distal end, indicating that the vessel may present a completely occlusive lesion, resulting in complete inability of blood flow therethrough. Stage 1: it means that the part of the angiostenosis part with the contrast agent is developed, but the contrast agent can not reach the far end of the angio well, which indicates that the angio stenosis is heavier and has lesion close to occlusion. And 2, stage: the contrast agent can fill the blood vessel and can make the blood vessel develop, but the developing speed is slower than that of the normal blood vessel, and the coronary artery is indicated to have certain stenosis or lesion. And 3, level: it means that the contrast agent can fill the blood vessel rapidly and completely, and the blood vessel morphology is displayed, and the TIMI3 grade is the normal blood flow state. In such another exemplary embodiment of blood flow fractionation, the numerical size of the fractionation represents the size of the thrombus as opposed to the 5-stage TIMI thrombus fractionation of the previous example of the present application, and in practice, the correspondence of the fractionation data may be adjusted to correctly represent the correspondence of the TIMI fractionation data to the high thrombus load condition. In other words, the more severe the high thrombotic load condition, the more severe the thrombotic symptoms represented by the TIMI classification data.
In the following technical scheme, the grade 5 TIMI thrombus classification method in the previous examples of the present application is taken as an example.
In an embodiment of the present application, the data for confirming the TIMI thrombus grade corresponding to the high thrombus load state includes: age index, gender index, hypertension index, BMI index, complication index, and the like. Wherein, the age index can be age/10, the gender index can be 1 (corresponding to male) and 0 (corresponding to female), the hypertension index can be a ratio of systolic pressure to systolic pressure of hypertension standard (or a ratio of a blood pressure mean value to a hypertension standard mean value, a ratio of diastolic pressure to a hypertension diastolic pressure standard, taking hypertension as diastolic pressure more than or equal to 80mmHg and systolic pressure more than or equal to 130mmHg as examples), the BMI index can be a BMI value, and the complication incidence index can be a complication incidence probability (1 (corresponding to onset) or 0 (corresponding to non-onset)). The complicating diseases at least comprise hypertension, cardiogenic shock, atrial fibrillation, periodontal disease and the like.
In exemplary embodiments, the concurrent disease may also include cerebral infarction, diabetes. It should be appreciated that any potentially relevant concurrent disease data may be input in training the machine model, as desired.
In an exemplary embodiment, TIMI thrombus levels can be predicted using high thrombus loading conditions. It should be noted that the value of the index may be adjusted as needed when training the machine-learned model, and need not be the value in the above exemplary embodiment. When the machine model is trained, a predetermined rule can be selected for each index in each piece of data used for training to be used as a value, and when the machine learning model is applied, the value conforming to the predetermined rule can be output to be used for obtaining a high thrombus load state and calculating a TIMI thrombus level.
The TIMI thrombus grade was calculated using the following formula: TIMI =5 t/(1 + t), t = e ^ (0.0605 + age index +0.1048 + sex index +1.2045 + hypertension index-0.0578 + bmi index-0.3305 + cardiogenic shock onset index-0.5592 + atrial fibrillation onset index-0.7823 + periodontal disease onset index), and t represents a high thrombotic load state. Based on statistical and clinical data of a large number of patients used to train the machine model, a data set is established for each patient, the data set comprising a plurality of values assigned to the patient's age, sex, hypertension, BMI, whether cardiogenic shock has occurred, whether atrial fibrillation has occurred, and whether periodontal disease has occurred. Each data set also includes the measured TIMI thrombus level for the corresponding patient, again expressed as a numerical value of 0-5 (the numerical value can be adjusted according to the criteria for TIMI thrombus classification). And drawing a fitting curve through a machine learning model so as to establish the above equation relation between the TIMI thrombus level of the patient and the age, sex, hypertension, BMI, whether cardiogenic shock occurs, whether atrial fibrillation occurs and whether periodontal disease occurs. When new data on the age, sex, hypertension, BMI, onset of cardiogenic shock, onset of atrial fibrillation and onset of periodontal disease of a patient are obtained, the TIMI thrombus level of the patient can be estimated. The numerical value of the TIMI thrombus level calculated according to this formula may be rounded down to obtain an integer TIMI thrombus level.
Before the application of the solution of the present application, analysis has been performed on the basis of the data of the aforementioned three thousand patients, confirming that the patient has HTB (high thrombotic burden) for patients with TIMI thrombotic grade classification of grade 2 to 5, and RTB (regular thrombotic burden) for patients with thrombotic grade classification below grade 2. Prior to training, a corresponding high thrombotic load status has been set according to the TIMI thrombotic grade or the patient's thrombotic status. Thus, in the application of the model, after outputting a high thrombus load status (reading or grading), the corresponding TIMI thrombus grade can be determined.
The decision block 17 is adapted to decide on the basis of the TIMI thrombus level, the mode of applying an anti-thrombotic therapy. In other words, after obtaining the TIMI thrombus level, it is already possible to understand the patient's thrombus status, and thereby perform a judgment as to whether or not to apply an antithrombotic therapy.
For example, when more than three thousand data including age, sex, BMI, hypertension data, whether cardiogenic shock occurs, whether atrial fibrillation occurs, and whether periodontal disease occurs are used to train a machine learning model with data of TIMI thrombus grade (grade 0-5) corresponding to a patient, the age index takes age/10, the sex index may take 1 (corresponding to male) and 0 (corresponding to female), the hypertension index takes the ratio of systolic pressure to systolic pressure of hypertension standard, the BMI index takes BMI value, and the complication disease occurrence index takes whether complication disease occurs (takes 1 (corresponding to occurrence) or 0 (corresponding to non-occurrence)) in training. The trained model is then applied. After inputting the age, sex, BMI, hypertension data, whether cardiogenic shock occurs, whether atrial fibrillation occurs and whether periodontal disease occurs of a new myocardial infarction patient into the trained model, the TIMI =5 t/(1 t), t = e ^ (0.0605 age index +0.1048 gender index +1.2045 hypertension index-0.0578 BMI index-0.3305 cardiogenic shock occurrence index-0.5592 atrial fibrillation occurrence index-0.7823 periodontal disease occurrence index), and t represents a high thrombus load state, calculating the TIMI thrombus level of the myocardial infarction patient, confirming whether antithrombotic therapy is applied or confirming the mode of applying antithrombotic therapy.
In an example, the patient is a 70-year-old male with a systolic blood pressure of 140mmHg, a BMI of 18kg/m, and the onset of cardiogenic shock, atrial fibrillation and non-onset of periodontal disease are shown. These data are obtained from statistical and clinical data of the patient. These data are input into a trained model. The age index value is 70/10=7, the sex index value is 1, the hypertension index value is 140/130=1.077, the BMI index value is 18, the cardiogenic shock onset index value is 1, the atrial fibrillation onset index value is 1, and the periodontal disease onset index value is 0. The high thrombus load condition t was calculated to be 0.901, the patient had a value of the TIMI thrombus grade of 2.37, and the patient was rounded down to confirm that the TIMI thrombus grade was 2. Further, whether or not an antithrombotic therapy is applied, or the mode of applying an antithrombotic therapy can be confirmed.
In such a way, the cardiovascular medical data analysis realized by machine learning is introduced, and whether the antithrombotic treatment is applied to the myocardial infarction patient is judged according to the detailed illness state of the myocardial infarction patient, so that the burden of determining a treatment mode is reduced, the risk of cardiovascular disease complications is reduced, and the treatment effect is improved. Machine learning approaches that analyze large data make it easy to determine high thrombus loading conditions.
Fig. 2 is a block diagram of an apparatus for cardiovascular medical data analysis according to an exemplary embodiment of the present application. As shown in fig. 2, according to an exemplary embodiment of the present application, the determination module 17 includes a first determination unit 171 and a second determination unit 173. The first judgment unit 171 is configured to determine to apply an antithrombotic therapy if the TIMI thrombus level is greater than or equal to 3. The second decision unit 173 is used for determining not to apply the anti-thrombotic therapy if the TIMI thrombus grade is less than grade 3. The first and second determination units 171 and 173 of the determination module 17 adopt the TIMI thrombus level 3 as a boundary whether or not the antithrombotic treatment is applied. In the present solution, HTB is an independent predictor of mortality (risk ratio [ HR ] 1.76, p = 0.023) and Major Adverse Cardiovascular Events (MACE) (HR 1.88, p = 0.001). Among the many patients receiving PCI (percutaneous coronary intervention) due to STEMI, patients undergoing antithrombotic therapy such as thrombus aspiration (thrombus aspiration is considered a simple method to remove thrombus prior to stent placement, thereby reducing distal embolization and improving prognosis) had a cardiovascular mortality of 2.4% within 30 days, while the corresponding data, not undergoing antithrombotic therapy, was 2.9% for patients who were simply subjected to PCI (risk ratio, 0.84% ci, 0.70-1.01 p =. In patients with high thrombotic load (TIMI thrombotic grade ≥ 3), thrombus aspiration is associated with reduced cardiovascular death (2.5% versus 3.1%; risk ratio, 0.80% ci, 0.65-0.98 p = 0.03. Therefore, the present solution uses TIMI classification 3 as a demarcation for the application of antithrombotic therapy to reduce the treatment risk of HTB patients. It will be appreciated that other TIMI stratification data may be selected as a boundary between whether anti-thrombotic therapy is applied, depending on the actual therapeutic or analytical needs.
In this way, whether or not the antithrombotic treatment is applied is determined by judging the thrombus state, the execution standard is effective and accurate, and the data is easy to acquire.
Fig. 3 is a block diagram of an apparatus for cardiovascular medical data analysis according to another exemplary embodiment of the present application. As shown in fig. 3, the apparatus 1 for cardiovascular medical data analysis according to an exemplary embodiment of the present application further comprises a second acquisition module 12, a comparison module 14 and a second validation module 16.
The second obtaining module 12 is configured to obtain the attack time and the attack time reference value of the myocardial infarction patient. The comparison module 14 is used for comparing the attack time with the attack time reference value to obtain an attack time comparison result. The second confirmation module 16 is used to determine whether to apply percutaneous coronary intervention based on the time of onset comparison.
The technical scheme of the application avoids the PCI, especially HTB patients, to be executed immediately after the onset of the disease. For example, in an exemplary embodiment, applying PCI to a patient immediately within 6 hours of the patient's onset would be a risk to the patient's treatment. For example, HTB STEMI patients will exhibit a state of stress and hypercoagulation immediately after disease onset when PCI is applied, while excessive intravascular device placement may trigger inflammatory and coagulation cascades that trigger thrombosis and thrombotic storms. In an exemplary embodiment, the patient has a time of onset of a year at month B, day C, D, and the time of onset reference is the current date at day a 'year at month B', day C ', D'. Determining to apply PCI to the patient if the time to onset reference a 'year B' month C 'day D' minus the time to onset a year B month C day D is at least 6 hours. If the time to onset reference a 'year B' month C 'day D' minus the time to onset a year B month C day D is less than 6 hours, then it is determined that PCI is not to be applied to the patient. In another exemplary embodiment, the patient's time of onset is at a year, month B, day C, D, and the time of onset reference is at a year, "B" month, C, "day D" at which PCI is expected to be applied. In other words, if the comparison result indicates that the time from the onset time to the onset time reference value has exceeded 6 hours, it is determined that PCI is applied to the patient, and conversely, PCI is not applied to the patient. It should be understood that the time difference of 6 hours is only an example adopted in the present application, and the time can be adjusted according to the situation and requirement when the technical solution is actually applied, and thus is not limited thereto. For example, the time difference may be several minutes or as long as several days, taking into account other factors that may be safe for the patient to treat.
Fig. 4 is a block diagram of an apparatus for cardiovascular medical data analysis according to yet another exemplary embodiment of the present application. As shown in fig. 4, according to an exemplary embodiment of the present application, the second confirmation module 16 includes a first confirmation unit 161 and a second confirmation unit 163.
The first confirming unit 161 is configured to determine to apply the percutaneous coronary intervention if the onset time comparison result indicates that the onset time is greater than the onset time reference value. And a second confirming unit 163 for determining that the percutaneous coronary intervention is not applied if the onset time comparison result indicates that the onset time is less than or equal to the onset time reference value.
In another embodiment, the attack time is a time from the attack time of the patient to the present time, and the attack time reference value is a preset length of time. For example, if the attack time is 7 hours from the attack time to the current time, and the attack time reference value is 6 hours, the PCI is determined to be applied. If the attack time is 4 hours that have passed from the attack time to the current time by the patient and the attack time reference value is 6 hours, it is determined that PCI is not applied. The onset time may be provided via a smart device, such as a bracelet of the patient (the patient is recorded when the reading indicates the onset), or may be input via a mobile phone, a computer, or may be provided via a medical system of the hospital.
In this way, whether to apply percutaneous coronary intervention treatment is determined based on the attack time of the myocardial infarction patient, the risk of complications brought to the treatment of the myocardial infarction patient is reduced, and the treatment effect is improved. The comparison of the attack time with the attack time reference value is performed such that it can be automatically determined whether or not the percutaneous coronary intervention is applied, thereby improving the ease of use of the data analysis device.
According to an exemplary embodiment of the present application, a method of cardiovascular medical data analysis is also provided. Fig. 5 is a flow chart of a method of cardiovascular medical data analysis according to an embodiment of the application. As shown in fig. 5, the method for analyzing cardiovascular medical data is applied to any one of the above devices for analyzing cardiovascular medical data, and the method for analyzing cardiovascular medical data includes: in step S10, statistical data and clinical data of the myocardial infarction patient are obtained, the statistical data at least comprises age, gender, BMI, and concurrent diseases, and the clinical data at least comprises: diagnostic results, laboratory test results. In step S20, the high thrombus burden state of the patient is calculated by a model trained in advance based on statistical data and clinical data. In step S30, a TIMI thrombus level corresponding to a high thrombus load state is confirmed based on the TIMI thrombus classification data. In step S40, based on the TIMI thrombus level, the mode of applying the antithrombotic therapy is judged.
Fig. 6 is a flow chart of a method of cardiovascular medical data analysis according to an exemplary embodiment of the present application. As shown in fig. 6, according to an exemplary embodiment of the present application, determining the manner of applying the anti-thrombotic therapy based on the TIMI thrombus level at step S40 includes: in step S41, if the TIMI thrombus level is greater than or equal to level 3, it is determined that the intensive antithrombotic therapy is applied. And determining to apply a conventional anti-thrombotic therapy if the TIMI thrombus level is less than grade 3 at step S42.
The enhanced antithrombotic therapy refers to increasing one or more of the doses of the medicines on the basis of the conventional antithrombotic therapy, or combining intravenous pumping of tirofiban (or eptifibatide). Conventional antithrombotic therapy refers to oral administration of aspirin and clopidogrel (or ticagrelor), subcutaneous injection of low molecular heparin or fondaparinux sodium, or continuous intravenous pumping of heparin.
According to an exemplary embodiment of the application, the method of cardiovascular medical data analysis further comprises: and acquiring the attack time and the attack time reference value of the myocardial infarction patient. And comparing the attack time with the attack time reference value to obtain an attack time comparison result. Whether to apply percutaneous coronary intervention is determined based on the comparison result of the onset time.
According to an exemplary embodiment of the present application, determining whether to apply percutaneous coronary intervention treatment based on the morbidity time comparison result includes: and if the compared result of the attack time indicates that the attack time is greater than the reference value of the attack time, determining to apply the percutaneous coronary intervention treatment. And if the incidence time comparison result indicates that the incidence time is less than or equal to the incidence time reference value, determining that the percutaneous coronary intervention treatment is not applied.
By implementing the method, the TIMI evaluation path can be directly and conveniently provided, and a quick and accurate implementation mode is provided for diagnosis and clinical evaluation.
The method for cardiovascular medical data analysis according to the exemplary embodiment of the present application has been described in the foregoing device for cardiovascular medical data analysis, and will not be described herein again.
According to an exemplary embodiment of the application, an apparatus for cardiovascular medical data analysis comprises a computer storage medium comprising computer readable instructions which, when executed by one or more processors, perform the method of any of the above.
According to an example embodiment of the present application, a computer storage medium includes computer readable instructions that, when executed by one or more processors, perform the method of any one of the above.
In an exemplary embodiment, the method for analyzing cardiovascular medical data according to the technical solution of the present application is designed as software on a mobile phone APP or a PC, data to be acquired is input through a keyboard, a mouse or voice, and data may also be acquired from a device (e.g., a bracelet, a smart watch, a smart medical instrument, etc.) worn by a patient through a wireless connection (e.g., bluetooth, wifi, 5G, etc.).
In an exemplary embodiment, the trained model is applied to calculate the high thrombus burden state of the patient by a method that provides cardiovascular medical data analysis through software on a server or PC, APP on a cell phone, or the like. And the statistical data and clinical data of the patient can be obtained through software on a server or a PC, APP on a mobile phone and the like. In addition, the attack time of the patient can be directly obtained from the bracelet of the patient. Further, after determining whether to apply the anti-thrombus treatment and whether to apply the percutaneous coronary intervention treatment, the results of determining whether to apply the anti-thrombus treatment and whether to apply the percutaneous coronary intervention treatment can be directly displayed on a mobile phone, a bracelet or other portable devices of the patient, so as to prompt the patient or a doctor to execute a corresponding treatment mode. Therefore, doctors and patients can more easily master the information of the treatment process, the safety of the treatment process is improved, and the prognosis is improved.
In the embodiments of the present application, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to the related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units or modules is only one logical division, and there may be other divisions when the actual implementation is performed, for example, a plurality of units or modules or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of modules or units through some interfaces, and may be in an electrical or other form.
The units or modules described as separate parts may or may not be physically separate, and parts displayed as units or modules may or may not be physical units or modules, may be located in one place, or may be distributed on a plurality of network units or modules. Some or all of the units or modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional units or modules in the embodiments of the present application may be integrated into one processing unit or module, or each unit or module may exist alone physically, or two or more units or modules are integrated into one unit or module. The integrated unit or module may be implemented in the form of hardware, or may be implemented in the form of a software functional unit or module.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, or portions or all or portions of the technical solutions that contribute to the prior art, may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic disk, or an optical disk, and various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present application and it should be noted that those skilled in the art can make several improvements and modifications without departing from the principle of the present application, and these improvements and modifications should also be considered as the protection scope of the present application.
Claims (12)
1. An apparatus (1) for cardiovascular medical data analysis, characterized in that the apparatus (1) for cardiovascular medical data analysis comprises:
a first acquisition module (11) for acquiring statistical and/or clinical data of a myocardial infarction patient, the statistical data comprising at least age, sex, BMI and co-morbidities, the clinical data comprising at least: diagnostic results, laboratory test results;
a calculation module (13) for calculating a high thrombus burden state of the patient based on the statistical data and/or the clinical data by means of a pre-trained model;
a first confirming module (15) for confirming a TIMI thrombus grade corresponding to the high thrombus load state according to the TIMI thrombus grading data; and
a determination module (17) for determining whether to apply an anti-thrombotic therapy based on the TIMI thrombus level.
2. The device (1) for cardiovascular medical data analysis according to claim 1, wherein the concurrent disease is selected from one or more of hypertension, cardiogenic shock, atrial fibrillation and periodontal disease.
3. The apparatus (1) for cardiovascular medical data analysis according to claim 2, wherein the TIMI thrombus level is calculated using the following formula:
TIMI =5 t/(1 + t), t = e ^ (0.0605 + age index +0.1048 + sex index +1.2045 + hypertension index-0.0578 + bmi index-0.3305 + cardiogenic shock onset index-0.5592 + atrial fibrillation onset index-0.7823 + periodontal disease onset index), and t represents a high thrombotic load state.
4. The cardiovascular medical data analysis apparatus (1) according to any of claims 1-3, wherein said determining means (17) comprises:
a first determination unit (171) for determining to apply an enhanced antithrombotic treatment if the TIMI thrombus level is greater than or equal to level 3; and
a second decision unit (173) for determining to apply a conventional anti-thrombotic therapy if the TIMI thrombus grade is less than grade 3.
5. The cardiovascular medical data analysis apparatus (1) according to any of claims 1-3, wherein the cardiovascular medical data analysis apparatus (1) further comprises:
a second obtaining module (12) for obtaining the attack time and the attack time reference value of the myocardial infarction patient;
the comparison module (14) is used for comparing the attack time with the attack time reference value to obtain an attack time comparison result; and
a second confirmation module (16) for determining whether to apply a percutaneous coronary intervention based on the onset time comparison result.
6. The apparatus (1) for cardiovascular medical data analysis according to claim 5, wherein the second validation module (16) comprises:
a first confirmation unit (161) for determining to apply a percutaneous coronary intervention if the onset time comparison result indicates that the onset time is greater than the onset time reference value; and
a second confirmation unit (163) for determining that no percutaneous coronary intervention is applied if the onset time comparison result indicates that the onset time is less than or equal to the onset time reference value.
7. A method for cardiovascular medical data analysis, wherein the method for cardiovascular medical data analysis is applied to the apparatus for cardiovascular medical data analysis of any one of claims 1-6, and the method for cardiovascular medical data analysis comprises:
step S10, obtaining statistical data and clinical data of the myocardial infarction patient, wherein the statistical data at least comprises age, gender, BMI and concurrent diseases, and the clinical data at least comprises: diagnostic results, laboratory test results;
step S20, calculating the high thrombus load state of the patient through a pre-trained model based on the statistical data and the clinical data;
step S30, confirming a TIMI thrombus grade corresponding to the high thrombus load state according to the TIMI thrombus grading data; and
step S40, based on the TIMI thrombus level, judging the mode of applying antithrombotic therapy,
wherein the TIMI thrombus grade is calculated using the following formula:
TIMI =5 t/(1 + t), t = e ^ (0.0605 age index +0.1048 gender index +1.2045 hypertension index-0.0578 BMI index-0.3305 cardiogenic shock onset index-0.5592 atrial fibrillation onset index-0.7823 periodontal disease onset index), and t represents a high thrombus load state.
8. The method of cardiovascular medical data analysis of claim 7, wherein said step S40, based on said TIMI thrombus level, determining the manner in which to apply an anti-thrombotic therapy comprises:
step S41, determining to apply an enhanced antithrombotic therapy if the TIMI thrombus level is greater than or equal to level 3; and
step S42, determining to apply a conventional anti-thrombotic therapy if the TIMI thrombus level is less than grade 3.
9. The method of cardiovascular medical data analysis of claim 7, further comprising:
acquiring the attack time and an attack time reference value of the myocardial infarction patient;
comparing the attack time with the attack time reference value to obtain an attack time comparison result; and
determining whether to apply percutaneous coronary intervention based on the onset time comparison result.
10. The method of cardiovascular medical data analysis of claim 9,
the determining whether to apply percutaneous coronary intervention treatment based on the onset time comparison result includes:
determining to apply percutaneous coronary intervention if the attack time comparison result indicates that the attack time is greater than the attack time reference value; and
determining not to apply percutaneous coronary intervention if the onset time comparison result indicates that the onset time is less than or equal to the onset time reference value.
11. An apparatus for cardiovascular medical data analysis, comprising a computer storage medium comprising computer readable instructions which, when executed by one or more processors, perform the method of any of claims 7-10.
12. A computer storage medium comprising computer readable instructions which, when executed by one or more processors, perform the method of any one of claims 7-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310166383.9A CN115862793B (en) | 2023-02-27 | 2023-02-27 | Apparatus and method for cardiovascular medical data analysis, and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310166383.9A CN115862793B (en) | 2023-02-27 | 2023-02-27 | Apparatus and method for cardiovascular medical data analysis, and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115862793A true CN115862793A (en) | 2023-03-28 |
| CN115862793B CN115862793B (en) | 2023-05-12 |
Family
ID=85658981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310166383.9A Active CN115862793B (en) | 2023-02-27 | 2023-02-27 | Apparatus and method for cardiovascular medical data analysis, and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115862793B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292829A (en) * | 2023-10-13 | 2023-12-26 | 黄恺 | Graded diagnosis and treatment information system for coronary heart disease |
| CN117672495A (en) * | 2023-11-30 | 2024-03-08 | 北京医院 | Atrial fibrillation combined coronary heart disease patient long-term mortality prediction method based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013189822A1 (en) * | 2012-06-21 | 2013-12-27 | Luric Datenbank Gbr | Methods for determining the risk of mortality in patients with cardiovascular disease |
| US20160267243A1 (en) * | 2015-03-10 | 2016-09-15 | Abbott Cardiovascular Systems Inc. | Method and system for predicting risk of thrombosis |
| US20210251577A1 (en) * | 2020-02-17 | 2021-08-19 | Siemens Healthcare Gmbh | Machine-Based Risk Prediction for Peri-Procedural Myocardial Infarction or Complication from Medical Data |
| CN114550855A (en) * | 2020-11-25 | 2022-05-27 | 上海森亿医疗科技有限公司 | Venous thromboembolism prediction method, device, terminal and medium based on artificial intelligence |
-
2023
- 2023-02-27 CN CN202310166383.9A patent/CN115862793B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2013189822A1 (en) * | 2012-06-21 | 2013-12-27 | Luric Datenbank Gbr | Methods for determining the risk of mortality in patients with cardiovascular disease |
| US20160267243A1 (en) * | 2015-03-10 | 2016-09-15 | Abbott Cardiovascular Systems Inc. | Method and system for predicting risk of thrombosis |
| US20210251577A1 (en) * | 2020-02-17 | 2021-08-19 | Siemens Healthcare Gmbh | Machine-Based Risk Prediction for Peri-Procedural Myocardial Infarction or Complication from Medical Data |
| CN114550855A (en) * | 2020-11-25 | 2022-05-27 | 上海森亿医疗科技有限公司 | Venous thromboembolism prediction method, device, terminal and medium based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| 华为云开发者联盟: "基于自动机器学习的心脏病预测模型" * |
| 张红霞 等: "急性肺血栓栓塞的阻塞负荷：两种深度学习算法Qanadli评分和Mastora评分的比较" * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117292829A (en) * | 2023-10-13 | 2023-12-26 | 黄恺 | Graded diagnosis and treatment information system for coronary heart disease |
| CN117672495A (en) * | 2023-11-30 | 2024-03-08 | 北京医院 | Atrial fibrillation combined coronary heart disease patient long-term mortality prediction method based on artificial intelligence |
| CN117672495B (en) * | 2023-11-30 | 2024-05-14 | 北京医院 | Atrial fibrillation combined coronary heart disease patient long-term mortality prediction method based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115862793B (en) | 2023-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115862793B (en) | Apparatus and method for cardiovascular medical data analysis, and computer storage medium | |
| Chan et al. | Anticoagulation of pregnant women with mechanical heart valves: a systematic review of the literature | |
| US11923094B2 (en) | Monitoring predictive models | |
| US20030117296A1 (en) | Method and apparatus for multiple patient parameter variability analysis and display | |
| WO2019008798A1 (en) | Disease onset prediction device, disease onset prediction method, and program | |
| CN111297329B (en) | Method and system for predicting dynamic onset risk of cardiovascular complications of diabetics | |
| CN113171059B (en) | Postoperative END risk early warning of multi-modal monitoring information and related equipment | |
| CN112117008A (en) | Health monitoring method and system based on big data | |
| CN113066574A (en) | Neural network-based aneurysm rupture prediction method, device and storage medium | |
| CN115602312A (en) | Postoperative rehabilitation scheme generation method and device, electronic equipment and storage medium | |
| Kim et al. | Deep learning model for predicting intradialytic hypotension without privacy infringement: a retrospective two-center study | |
| Acharya et al. | A systems approach to cardiac health diagnosis | |
| US20230142909A1 (en) | Clinically meaningful and personalized disease progression monitoring incorporating established disease staging definitions | |
| US20210257102A1 (en) | Method for determining vascular access risk in a hemodialysis patient population | |
| CN112734717A (en) | Vascular access monitoring method and system for dialysis patients | |
| KR101584623B1 (en) | System and method for providing health management service | |
| CN113223713A (en) | Dynamic monitoring method, system and storage medium based on risk assessment | |
| WO2011021163A1 (en) | Medication and/or treatment regimen compliance | |
| CN111489828A (en) | Method for screening thrombus forming factors after fracture | |
| JP7451278B2 (en) | Medical information processing device, medical information processing method, and medical information processing program | |
| CN116230243B (en) | Plugging operation diagnosis and treatment system for refractory epileptic patient with high shunt capacity PFO patient | |
| Nath | In the Limelight: August 2022 | |
| Kraushaar et al. | A novel principled method for the measurement of vascular robustness uncovers hidden risk for premature CVD death | |
| WO2023068049A1 (en) | Prediction system, prediction device, and prediction method | |
| CN117373664B (en) | Coronary artery postoperative dangerous data analysis early warning system based on digital therapy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |